Triple

T10564036
Position Surface form Disambiguated ID Type / Status
Subject IPA III E249301 entity
Predicate predecessor P97 FINISHED
Object IPA II E249301 NE FINISHED

How this triple was built (2 steps)

Every LLM step that produced this triple, in pipeline order — named-entity classification, the disambiguation choices (the exact options shown, with the pick highlighted), and the generated description. The batch + timestamp of each is in the Provenance table below.

NER Named-entity recognition gpt-5-mini
Instruction
Given a phrase, classify it is english named entity (e.g., persons, organizations, works of art) in Latin script, or not (e.g., literals, dates, URLs, verbose phrases). For disambiguation, the statement where the phrase occurs as object is also given. Please return a JSON object with `phrase` (string, the phrase being analyzed) and `is_ne` (boolean, indicating whether the phrase is a Named Entity).
Input
Phrase: IPA II | Statement: [IPA III, predecessor, IPA II]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: IPA II
Context triple: [IPA III, predecessor, IPA II]
  • A. IPA III chosen
    IPA III is the European Union’s current funding instrument that supports pre-accession assistance to candidate and potential candidate countries for EU membership.
  • B. IPA
    IPA is the commonly used abbreviation for the International Publishers Association, a global trade organization representing book and journal publishers worldwide.
  • C. IPA
    IPA is the abbreviation for the United Kingdom government’s Infrastructure and Projects Authority, which oversees major public infrastructure and transformation projects.
  • D. IPP
    IPP (Internet Printing Protocol) is a modern network printing protocol that supports advanced features like secure, authenticated printing and detailed job management over IP-based networks.
  • E. IPS
    IPS is the National Rail station code used to identify Ipswich railway station in Suffolk, England.
  • F. None of above.
  • G. Unsure - the case is ambiguous/there is not enough information to decide.

Provenance (3 batches)

The batch behind each pipeline step, in order, with when it ran. Timestamps are batch-level — stages were processed in waves, so the object chain (NER → NED1 → NEDg → NED2) reads in order, but predicate / elicitation batches can sit in a different wave.

Step Stage Batch ID Status When
creating Elicitation batch_69d381c8bd708190acf3d275c908251e completed April 6, 2026, 9:50 a.m.
NER Named-entity recognition batch_69d527224b808190b996ae970393f9c3 completed April 7, 2026, 3:47 p.m.
NED1 Entity disambiguation (via context triple) batch_69d9349bb7748190b5afb492e78d1128 completed April 10, 2026, 5:34 p.m.
Created at: April 6, 2026, 12:36 p.m.